This paper studies this problem and proposes to incorporate chemical domain knowledge, specifically related to chemical reactions, for learning effective molecular representations.
For unsupervised semantic segmentation of urban scenes, our method surpasses the previous state-of-the-art baseline by +7. 14% in mIoU on Cityscapes and +6. 65% on KITTI.
1 code implementation • 16 Sep 2022 • Lanqing Li, Liang Zeng, Ziqi Gao, Shen Yuan, Yatao Bian, Bingzhe Wu, Hengtong Zhang, Yang Yu, Chan Lu, Zhipeng Zhou, Hongteng Xu, Jia Li, Peilin Zhao, Pheng-Ann Heng
The last decade has witnessed a prosperous development of computational methods and dataset curation for AI-aided drug discovery (AIDD).
Motivated by this observation, we propose a principled GCL framework on Imbalanced node classification (ImGCL), which automatically and adaptively balances the representations learned from GCL without labels.
Traffic forecasting is crucial for public safety and resource optimization, yet is very challenging due to three aspects: i) current existing works mostly exploit intricate temporal patterns (e. g., the short-term thunderstorm and long-term daily trends) within a single method, which fail to accurately capture spatio-temporal dependencies under different schemas; ii) the under-exploration of the graph positional encoding limit the extraction of spatial information in the commonly used full graph attention network; iii) the quadratic complexity of the full graph attention introduces heavy computational needs.
Besides, we propose a novel encoder-decoder architecture to incorporate the cross-time dynamic graph-based GCN for multi-step traffic forecasting.
However, without node content (i. e., side information) for training, the user (or item) specific representation can not be learned in the inductive setting, that is, a model trained on one group of users (or items) cannot adapt to new users (or items).
Ranked #3 on Recommendation Systems on MovieLens 1M
In a set of experiments on three real-world financial markets: stocks, cryptocurrencies, and ETFs, LARA significantly outperforms several machine learning based methods on the Qlib quantitative investment platform.
Extensive experiments on node classification, graph classification, and edge prediction demonstrate the effectiveness of AKE-GNN.
Learning sparse coordination graphs adaptive to the coordination dynamics among agents is a long-standing problem in cooperative multi-agent learning.
Methods: Our deep learning model, called AnatomyNet, segments OARs from head and neck CT images in an end-to-end fashion, receiving whole-volume HaN CT images as input and generating masks of all OARs of interest in one shot.